Computationally Efficient Data-Driven Discovery and Linear Representation of Nonlinear Systems For Control

Code

• github.com/tiwari-research-group/koopman-control-no-decoder
  OfficialIn papernone★ 3

Abstract

This work focuses on developing a data-driven framework using Koopman operator theory for system identification and linearization of nonlinear systems for control. Our proposed method presents a deep learning framework with recursive learning. The resulting linear system is controlled using a linear quadratic control. An illustrative example using a pendulum system is presented with simulations on noisy data. We show that our proposed method is trained more efficiently and is more accurate than an autoencoder baseline.

Reproductions